Temporal Smoothing Learning
-
- Shibata Katsunari
- Tokyo Institute of Technology
-
- Okabe Yoichi
- University of Tokyo
Bibliographic Information
- Other Title
-
- 時間軸スムージング学習
- ジカンジク スムージング ガクシュウ
Search this article
Abstract
In order to realize the mapping from spatial information to temporal information, Temporal Smoothing (TS) Learning is proposed. In this learning, the output of a learning unit, to which sensory signals are given as input, is trained to be smooth along time. In other words, the learning unit is trained so as that the second time derivative of the output itself becomes 0.<br>This learning can be applied to integrate local sensory signals into an analog spatial signal. It also can be used that an agent learn evaluation function in delayed reinforcement learning on behalf of TD Learning(8)(7) when only one target state is chosen. When a neural network was employed as a learning unit and visual signals were given as inputs directly, the hidden neurons in the neural network represented spatial information and had a adaptability of changing the representation according to the agent's motion characteristics.
Journal
-
- IEEJ Transactions on Electronics, Information and Systems
-
IEEJ Transactions on Electronics, Information and Systems 117 (9), 1291-1299, 1997
The Institute of Electrical Engineers of Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390001204607145472
-
- NII Article ID
- 130006843079
- 10006080329
- 10002811498
-
- NII Book ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL BIB ID
- 4284312
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed